Offline text-to-speech for Mac with local voice cloning and no cloud uploads
AI-powered speech-to-text that transforms your voice into polished writing in any app
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
FR
Pricing model
Freemium
Freemium
Pricing
Free: $0 (up to 1,000 characters per synthesis, single file export, one custom voice, limited background processing). Pro Monthly: $6.99. Pro Yearly: $29.99. Pro Lifetime: $49.99 (unlimited generations up to 20,000 characters, unlimited custom voices, unlimited batch exports, unlimited background pr
Swifly Basic: Free (20,000 words per month, or 2,000 with Privacy Mode). Swifly Pro: €15 per month or €144 per year (€12 per month billed annually), with unlimited words per week and team features. Swifly Enterprise: Contact for pricing.
Key features
185 English voices with various accents
Local voice cloning from 6-10 second audio samples
Batch export to MP3, WAV, AIFF, and M4A
Background queue for multiple synthesis jobs
Import from TXT, Markdown, DOCX and more file formats
Project workflow for long-form content and PDFs
Light and dark mode support
Uses less than 2GB of RAM
AI Speech Polish: transforms raw speech into clear, structured writing with automatic punctuation and phrasing
Smart Dictionary: learns unique vocabulary, names, brands and technical terms
Works in any app seamlessly without switching tools
Supports 100+ languages with instant transcription
Translation: dictate in one language and write in another
Magic Polish: clean up or translate selected text with one click
Enterprise-grade accuracy with reliable, precise writing
Privacy Mode with zero data retention and cloud processing
What makes it different
Completely offline operation with no cloud uploads or data transmission
One-time purchase option with lifetime access
MIT-licensed Chatterbox Turbo model with expressive output
Privacy-focused design built for creators who value control
Works in any application without switching between tools
Automatically adapts tone and formatting based on the app context
Supports over 100 languages with automatic language detection
Learns personal vocabulary and technical terms for greater accuracy